internal-link-optimizer

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes a helper script scripts/sitemap_urls.py that performs network requests using the urllib.request module to fetch XML sitemap files from external URLs provided by the user.
  • [COMMAND_EXECUTION]: The skill workflow involves executing a local Python script (scripts/sitemap_urls.py) to extract and list URLs from sitemaps for further analysis by the agent.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sitemaps. While this creates an attack surface where an attacker could theoretically place malicious instructions within a sitemap's URL paths, the risk is inherent to the skill's primary function of web content analysis.
  • Ingestion points: External XML sitemaps fetched by scripts/sitemap_urls.py.
  • Boundary markers: None explicitly defined in the script output for the agent.
  • Capability inventory: The agent has Read and Write tool access and the ability to execute the provided Python helper script.
  • Sanitization: The script performs basic XML parsing to extract URL locations but does not implement specific sanitization against embedded natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:38 PM